Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code and parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     münchen
    -0.07
    abı
    -0.07
     anlaşma
    -0.07
     unanimous
    -0.07
    这件事情
    -0.07
     reservation
    -0.07
    أكل
    -0.07
     hbox
    -0.06
     Pelosi
    -0.06
     Cyprus
    -0.06
    POSITIVE LOGITS
    Execution
    0.07
    Queries
    0.07
    IPLE
    0.07
    拭
    0.07
    istributions
    0.07
    庄
    0.07
     exercises
    0.07
    _REST
    0.07
    你
    0.07
     Support
    0.07
    Act Density 0.023%

    No Known Activations